Please wait a minute...
Advanced Search
数据分析与知识发现  2017, Vol. 1 Issue (9): 16-27     https://doi.org/10.11925/infotech.2096-3467.2017.09.02
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
什么样的评论更容易获得有用性投票*——以亚马逊网站研究为例
吴江, 刘弯弯
武汉大学信息管理学院 武汉 430079
武汉大学电子商务研究与发展中心 武汉 430079
Identifying Reviews with More Positive Votes——Case Study of Amazon.cn
Wu Jiang, Liu Wanwan
School of Information Management, Wuhan University, Wuhan 430072, China
The Center of E-commerce Research and Development of Wuhan University, Wuhan 430072, China
全文: PDF (550 KB)   HTML ( 2
输出: BibTeX | EndNote (RIS)      
摘要 

目的】购物网站评论系统中的投票机制有利于帮助消费者筛选出高质量评论。本文以评论有用性投票数为研究对象, 探讨什么样的评论更容易获得有用性投票。【方法】以信息采纳理论和负面偏差理论为基础, 基于亚马逊购物网站中的12 393条手机评论数据, 结合文本分析与零膨胀负二项回归分析方法, 从评论者信度、评论信息质量、评论极性三个方面探究评论有用性投票影响因素。【结果】研究结果表明, 评论者有用性、评论信息量、评论回复数、极端评分、评论文本消极倾向对评论有用性投票数具有积极正向影响。评论者发表评论数、评论者是否确认购买对评论有用性投票数有负向影响。【局限】仅以手机这一搜索型产品为研究对象, 研究结果欠缺普适性。【结论】本文研究成果对于改善电子商务评论排序系统具有借鉴意义。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
吴江
刘弯弯
关键词 在线评论评论有用性评论投票    
Abstract

[Objective] This article examines online reviews attracting more positive votes from consumers, aiming to identify those high quality reviews based on the information adoption and negative bias theories. [Methods] First, we retrieved 12 393 reviews on cellphones from Amazon.cn. Then, we investigated the impacts of the review’s characteristics on the numbers of positive votes with the help of zero inflated negative binomial regression and text analysis methods. The characteristics we studied include reviewer’s credibility, review’s quality and extremity. [Results] The usefulness of the reviewer’s previous posting, the information quality of the reviews, the number of comments, the extreme ratings, and the negative level of the reviews helped them receive more positive votes. However, the reviewers bought the products or not, and the number of the previously posted reviews had negative influence on the number of votes. [Limitations] Only investigated cellphones in this study. [Conclusions] This paper helps E-commerce websites improve their review ranking algorithms.

Key wordsOnline Review    Online Review Helpfulness    Review Vote
收稿日期: 2017-05-23      出版日期: 2017-10-18
ZTFLH:  G203  
基金资助:*本文系国家自然科学基金项目“创新2.0超网络中知识流动和群集交互的协同研究”(项目编号: 71373194)的研究成果之一
引用本文:   
吴江, 刘弯弯. 什么样的评论更容易获得有用性投票*——以亚马逊网站研究为例[J]. 数据分析与知识发现, 2017, 1(9): 16-27.
Wu Jiang,Liu Wanwan. Identifying Reviews with More Positive Votes——Case Study of Amazon.cn. Data Analysis and Knowledge Discovery, 2017, 1(9): 16-27.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2017.09.02      或      http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2017/V1/I9/16
  评论有用性投票实证研究模型
变量类型 变量名 变量 变量解释
自变量 评论者有用性 reUse 评论者获得有用性投票数/
评论者获得的总投票数
评论者发表
评论数
reNum 评论者已经发布的评论的
总数
是否确认购买 buyornot 评论者是否确认在亚马逊
上购买商品(0表示未确
认购买; 1表示确认购买)
评论信息量 reInfo 评论文本所包含信息量
评论回复数 comment 评论下的回复总数
评分极性 rateGap 评分与平均评分差值的绝
对值
评论积极倾向 pos 积极词汇总数/评论长度
评论消极倾向 neg 消极词汇总数/评论长度
因变量 评论有用
性投票数
usefulNum 评论获得的有用性投票
总数
  变量设计
类别 变量名 平均值 标准差 最大值 最小值
评论者信度 usefulNum 1.70 13.77 755.00 0.00
reUse 0.37 0.38 1.00 0.00
reNum 9.91 27.73 781.00 1.00
buyornot 0.97 0.17 1.00 0.00
评论信息质量 reInfo 0.29 0.25 1.00 0.00
comment 0.19 0.81 44.00 0.00
评论极性 rateGap 1.01 0.81 3.41 0.03
pos 0.02 0.03 0.31 0.00
neg 0.01 0.02 0.18 0.00
零膨胀因子 time 417.72 265.92 973.00 0.00
rank 34.20 20.01 97.00 1.00
comNum 652.26 2495.11 6011.00 100.00
  描述性统计分析结果
reUse reNum buyornot reInfo comment rateGap pos neg comNum time rank
reUse 1.00 0.22 -0.06 0.01 0.08 0.07 0.00 0.02 -0.06 -0.01 -0.05
reNum 0.22 1.00 -0.05 0.00 0.00 -0.06 0.00 -0.01 0.02 0.00 0.02
buyornot -0.06 -0.05 1.00 0.02 -0.07 -0.10 0.02 -0.05 0.07 0.01 -0.06
reInfo 0.01 0.00 0.02 1.00 0.04 -0.06 -0.05 -0.04 -0.05 -0.02 0.01
comment 0.08 0.00 -0.07 0.04 1.00 0.08 -0.03 0.01 -0.13 -0.13 -0.07
rateGap 0.07 -0.06 -0.10 -0.06 0.08 1.00 -0.13 0.19 0.04 -0.01 0.08
pos 0.00 0.00 0.02 -0.05 -0.03 -0.13 1.00 -0.13 -0.08 -0.07 0.00
neg 0.02 -0.01 -0.05 -0.04 0.01 0.19 -0.13 1.00 0.00 0.00 0.02
comNum -0.06 0.02 0.07 -0.05 -0.13 0.04 -0.08 0.00 1.00 0.78 0.26
time -0.01 0.00 0.01 -0.02 -0.13 -0.01 -0.07 0.00 0.78 1.00 0.17
rank -0.05 0.02 -0.06 0.01 -0.07 0.08 0.00 0.02 0.26 0.17 1.00
  变量相关系数
模型1 模型2 模型3
系数 P值 系数 P值 系数 P值
(Intercept) -1.598 0.000 -1.576 0.000 -2.081 0.000
reUse 5.836 0.000 4.841 0.000 4.651 0.000
reNum -0.006 0.000 -0.005 0.000 -0.004 0.000
buyornot -1.445 0.000 -1.334 0.000 -1.152 0.000
reInfo 0.451 0.000 0.630 0.000
comment 0.476 0.000 0.441 0.000
rateGap 0.324 0.000
pos -2.136 0.001
neg 2.418 0.034
Log(theta) -0.961 0.000 -0.721 0.000 -0.640 0.000
零膨胀模型
(Intercept) -30.124 0.000 -30.445 0.000 -30.500 0.000
rank 0.043 0.000 0.0435 0.000 0.044 0.000
Log(time) 4.230 0.000 4.272 0.000 4.277 0.000
LogLike -12940 -12530 -12380
  回归分析结果
已发表评论数 比率 平均有用性投票数 评分差值(评分)
>1 63% 1.64 0.93(4.24)
1 37% 1.80 1.13(3.87)
  评论者发表评论数与有用性投票数关系
是否真实购买 比率 平均有用性投票数 评分差值(评分)
1 97% 1.51 1.00(4.16)
0 3% 7.73 1.46(3.33)
  评论者是否确认购买与有用性投票数关系
类别 假设 结果
评论者
信度
H1a: 评论者有用性对评论有用投票数有显著的正向影响。 支持
H1b: 评论者发表的评论数对评论有用性投票数有显著的正向影响 不支持
H1c: 评论者的购买的真实性对评论有用性投票数有显著的正向影响。 不支持
评论
信息
质量
H2a: 评论信息量对评论有用性投票数有显著的正向影响。 支持
H2b: 评论回复数对评论有用性投票数有显著的正向影响。 支持
评论
极性
H3a: 评分极性对评论有用性投票数有显著的正向影响。 支持
H3b: 评论文本消极情感倾向对评论有用性投票数有正向影响。 支持
H3c: 评论文本积极情感倾向对评论有用性投票数有负向影响。 支持
  假设结果
[1] Hu N, Bose I, Koh N S, et al.Manipulation of Online Reviews: An Analysis of Ratings, Readability, and Sentiments[J]. Decision Support Systems, 2012, 52(3): 674-684.
doi: 10.1016/j.dss.2011.11.002
[2] Kim S M, Pantel P, Chklovski T, et al.Automatically Assessing Review Helpfulness[C]//Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, Sydney, Australia. 2006: 423-430.
[3] Liu Y, Huang X, An A, et al.Modeling and Predicting the Helpfulness of Online Reviews[C]//Proceedings of the 8th IEEE International Conference on Data Mining. IEEE Computer Society, 2008, 15: 443-452.
[4] Mudambi S M, Schuff D.What Makes a Helpful Online Review? A Study of Customer Reviews on Amazon.com[J]. MIS Quarterly, 2010, 34(1): 185-200.
[5] Ghose A, Ipeirotis P G.Estimating the Helpfulness and Economic Impact of Product Reviews: Mining Text and Reviewer Characteristics[J]. IEEE Transactions on Knowledge & Data Engineering, 2011, 23(10): 1498-1512.
[6] Baek H, Ahn J, Choi Y.Helpfulness of Online Consumer Reviews: Readers’ Objectives and Review Cues[J]. International Journal of Electronic Commerce, 2012, 17(2): 99-126.
doi: 10.2753/JEC1086-4415170204
[7] Korfiatis N, García-Bariocanal E, Sánchez-Alonso S.Evaluating Content Quality and Helpfulness of Online Product Reviews: The Interplay of Review Helpfulness vs. Review Content[J]. Electronic Commerce Research & Applications, 2012, 11(3): 205-217.
doi: 10.1016/j.elerap.2011.10.003
[8] Yin D, Bond S D, Zhang H.Anxious or Angry? Effects of Discrete Emotions on the Perceived Helpfulness of Online Reviews[J]. MIS Quarterly, 2014, 38(2): 539-560.
[9] Greene W H.Econometric Analysis [M]. 北京: 清华大学出版社, 2001: 182-197.
[9] (Greene W H.Econometric Analysis [M]. Beijing: Tsinghua University Press, 2001: 182-197.)
[10] Sussman S W, Siegal W S.Informational Influence in Organizations: An Integrated Approach to Knowledge Adoption[J]. Information Systems Research, 2003, 14(1): 47-65.
doi: 10.1287/isre.14.1.47.14767
[11] 殷国鹏, 刘雯雯, 祝珊. 网络社区在线评论有用性影响模型研究——基于信息采纳与社会网络视角[J]. 图书情报工作, 2012, 56(16): 140-147.
[11] (Yin Guopeng, Liu Wenwen, Zhu Shan.What Makes a Helpful Online Review?——The Perspective of Information Adoption and Social Network[J]. Library & Information Service, 2012, 56(16): 140-147.)
[12] 黄卫来, 潘晓波. 在线商品评价信息有用性模型研究——纳入应用背景因素的信息采纳扩展模型[J]. 图书情报工作, 2014, 58(S1): 141-151.
[12] (Huang Weilai, Pan Xiaobo.The Research of the Information Usefulness of Online Product Reviews——The Extented Information Adoption Model with Background Factor[J]. Library & Information Service, 2014, 58(S1): 141-151. )
[13] 王军, 周淑玲. 一致性与矛盾性在线评论对消费者信息采纳的影响研究——基于感知有用性的中介作用和自我效能的调节作用[J]. 图书情报工作, 2016, 60(22): 94-101.
doi: 10.13266/j.issn.0252-3116.2016.22.014
[13] (Wang Jun, Zhou Shuling.Research on How the Consistent and Contradictory Online Reviews Affect Consumer Information Adoption——Based on the Mediating Effects of Perceived Usefulness and the Moderating Effects of Self-efficacy[J]. Library & Information Service, 2016, 60(22): 94-101.)
doi: 10.13266/j.issn.0252-3116.2016.22.014
[14] 宋雪雁, 王萍. 信息采纳行为概念及影响因素研究[J]. 情报科学, 2010, 28(5): 760-762, 767.
[14] (Song Xueyan, Wang Ping.Research on Concept and Effective Factors of Information Adoption Behavior[J]. Information Science, 2010, 28(5): 760-762, 767.)
[15] Taylor R S.Value-added Processes in Information Systems[M]. Norwood, NJ: Ablex, 1986.
[16] Hilligoss B, Rieh S Y.Developing a Unifying Framework of Credibility Assessment: Construct, Heuristics, and Interaction in Context[J]. Information Processing and Management, 2008, 44(4): 1467-1484.
doi: 10.1016/j.ipm.2007.10.001
[17] Gorla N, Somers T M, Wong B.Organizational Impact of System Quality, Information Quality, and Service Quality[J]. The Journal of Strategic Information Systems, 2010, 19(3): 207-228.
doi: 10.1016/j.jsis.2010.05.001
[18] Filieri R, Mcleay F.E-WOM and Accommodation: An Analysis of the Factors that Influence Travelers’ Adoption of Information from Online Reviews[J]. Journal of Travel Research, 2014, 53(1): 44-57.
doi: 10.1177/0047287513481274
[19] Kanouse D, Hansonn L.Negativity in Evaluations [M]. General Learning Press, 1972.
[20] Baumeister R F, Bratslavsky E, Finkenauer C, et al.Bad is Stronger than Good[J]. Review of General Psychology, 2001, 95(3): 477-509.
[21] Rozin P, Royzman E B. Negativity Bias, Negativity Dominance,Contagion[J]. Personality & Social Psychology Review, 2001, 5(4): 296-320.
[22] Zhu L, Yin G, He W.Is This Opinion Leader’s Review Useful? Peripheral Cues for Online Review Helpfulness[J]. Journal of Electronic Commerce Research, 2014, 15(4): 267-280.
[23] Levi A, Mokryn O.The Social Aspect of Voting for Useful Reviews [C]//Proceedings of the International Conference on Social Computing, Behavioral-Cultural Modeling, and Prediction.Springer International Publishing, 2014: 293-300.
[24] Kuan K K Y, Hui K L, Prasarnphanich P, et al. What Makes a Review Voted? An Empirical Investigation of Review Voting in Online Review Systems[J]. Journal of the Association for Information Systems, 2015, 16(1): 48-71.
[25] Lee S, Choeh J Y.Predicting the Helpfulness of Online Reviews Using Multilayer Perceptron Neural Networks[J]. Expert Systems with Applications, 2014, 41(6): 3041-3046.
doi: 10.1016/j.eswa.2013.10.034
[26] Holmqvist K, Holsanova J, Barthelson M, et al.Chapter 30-Reading or Scanning? A Study of Newspaper and Net Paper Reading [A]// Hyönä J, Radach R, Deubel H. The Mind’s Eye: Cognitive and Applied Aspects of Eye Movement Research[M]. 2003: 657-670.
[27] Schindler R M, Bickart B.Perceived Helpfulness of Online Consumer Reviews: The Role of Message Content and Style[J]. Journal of Consumer Behaviour, 2012, 11(3): 234-343.
doi: 10.1002/cb.1372
[28] Cao Q, Duan W, Gan Q.Exploring Determinants of Voting for the “Helpfulness” of Online User Reviews: A Text Mining Approach[J]. Decision Support Systems, 2011, 50(2): 511-521.
doi: 10.1016/j.dss.2010.11.009
[29] Forman C, Ghose A, Wiesenfeld B.Examining the Relationship Between Reviews and Sales: The Role of Reviewer Identity Disclosure in Electronic Markets[J]. Information Systems Research, 2008, 19(3): 291-313.
doi: 10.1287/isre.1080.0193
[30] Zhang J Q, Craciun G, Shin D.When does Electronic Word-of-mouth Matter? A Study of Consumer Product Reviews[J]. Journal of Business Research, 2010, 63(12): 1336-1341.
doi: 10.1016/j.jbusres.2009.12.011
[31] Cui G, Lui H K, Guo X.The Effect of Online Consumer Reviews on New Product Sales[J]. International Journal of Electronic Commerce, 2014, 17(1): 39-58.
doi: 10.2753/JEC1086-4415170102
[32] Siering M, Muntermann J.What Drives the Helpfulness of Online Product Reviews? From Stars to Facts and Emotions[C]// Proceedings of the 11th International Conference on Wirtschaftsinformatik.2013: 103-118.
[33] Erkan G, Radev D R.LexRank: Graph-based Lexical Centrality as Salience in Text Summarization[J]. Journal of Artificial Intelligence Research, 2004, 22(1): 457-479.
doi: 10.1613/jair.1523
[34] 纪文倩, 李舟军, 巢文涵, 等. 一种基于LexRank算法的改进的自动文摘系统[J]. 计算机科学, 2010, 37(5): 151-154.
doi: 10.3969/j.issn.1002-137X.2010.05.036
[34] (Ji Wenqian, Li Zhoujun, Chao Wenhan, et al.Automatic Abstracting System Based on Improved LexRank Algorithm[J]. Computer Science, 2010, 37(5): 151-154.)
doi: 10.3969/j.issn.1002-137X.2010.05.036
[35] Salton G, Buckley C.Term-weighting Approaches in Automatic Text Retrieval[J]. Information Processing & Management, 1988, 24(5): 513-523.
doi: 10.1016/0306-4573(88)90021-0
[36] Zhang H P, Yu H K, Xiong D Y, et al.HHMM-based Chinese Lexical Analyzer ICTCLAS[C]//Proceedings of the 2nd SIGHAN Workshop on Chinese Language Processing. Association for Computational Linguistics, 2003: 184-187.
[37] 台湾大学. 台湾大学NTUSD中文情感词典 [DS/OL]. [2016-03-24]. .
[37] (Taiwan Univeristy. NTUSD: The Chinese Emotion Word Library [DS/OL]. [2016-03-24].
[38] Dean C, Lawless J F.Tests for Detecting Overdispersion in Poisson Regression Models[J]. Journal of the American Statistical Association, 1989, 84(406): 467-472.
doi: 10.2307/2289931
[39] Greene W H.Accounting for Excess Zeros and Sample Selection in Poisson and Negative Binomial Regression Models [OL]. New York University Working Paper No.EC-94-10.
[40] Chevalier J A, Mayzlin D.The Effect of Word of Mouth on Sales: Online Book Reviews[J]. Journal of Marketing Research, 2006, 43(3): 345-354.
doi: 10.1509/jmkr.43.3.345
[41] Hu N, Zhang J, Pavlou P A.Overcoming the J-Shaped Distribution of Product Reviews[J]. Communications of the ACM, 2009, 52(10): 144-147.
doi: 10.1145/1562764
[1] 沈卓,李艳. 基于PreLM-FT细粒度情感分析的餐饮业用户评论挖掘[J]. 数据分析与知识发现, 2020, 4(4): 63-71.
[2] 余本功,张培行,许庆堂. 基于F-BiGRU情感分析的产品选择方法*[J]. 数据分析与知识发现, 2018, 2(9): 22-30.
[3] 李慧,胡云凤. 基于动态情感主题模型的在线评论分析*[J]. 数据分析与知识发现, 2017, 1(9): 74-82.
[4] 张艳丰, 李贺, 彭丽徽, 侯力铁. 基于情感语义特征抽取的在线评论有用性分类算法与应用[J]. 数据分析与知识发现, 2017, 1(12): 74-83.
[5] 杨海霞,吴维芳,孙含林. 基于STM分析旅行者对不同档次酒店的偏好差异[J]. 现代图书情报技术, 2016, 32(9): 51-57.
[6] 张艳丰,李贺,彭丽徽. 基于模糊情感计算的商品在线评论用户品牌转换意向研究*[J]. 现代图书情报技术, 2016, 32(5): 64-71.
[7] 高松,王洪伟,冯罡,王伟. 面向在线评论的比较观点挖掘研究综述*[J]. 现代图书情报技术, 2016, 32(10): 1-12.
[8] 聂卉, 王佳佳. 产品评论垃圾识别研究综述[J]. 现代图书情报技术, 2014, 30(2): 63-71.
[9] 孙霄凌, 赵宇翔, 朱庆华. 在线商品评论系统功能需求的Kano模型分析——以我国主要购物网站为例[J]. 现代图书情报技术, 2013, (6): 76-84.
[10] 李志宇. 在线商品评论效用排序模型研究[J]. 现代图书情报技术, 2013, (4): 62-68.
[11] 张红斌, 李广丽. 商品在线评价的情感倾向性分析研究[J]. 现代图书情报技术, 2012, (10): 61-66.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn